perf events, x86/stacktrace: Fix performance/softlockup by providing a special frame pointer-only stack walker

It's just wasteful for stacktrace users like perf to walk
through every entries on the stack whereas these only accept
reliable ones, ie: that the frame pointer validates.

Since perf requires pure reliable stacktraces, it needs a stack
walker based on frame pointers-only to optimize the stacktrace
processing.

This might solve some near-lockup scenarios that can be triggered
by call-graph tracing timer events.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1261024834-5336-2-git-send-regression-fweisbec@gmail.com>
[ v2: fix for modular builds and small detail tidyup ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 33 insertions, 3 deletions

diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 6c75151..35e8912 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -22,6 +22,12 @@ print_context_stack(struct thread_info *tinfo,
 		    const struct stacktrace_ops *ops, void *data,
 		    unsigned long *end, int *graph);
 
+extern unsigned long
+print_context_stack_bp(struct thread_info *tinfo,
+		       unsigned long *stack, unsigned long bp,
+		       const struct stacktrace_ops *ops, void *data,
+		       unsigned long *end, int *graph);
+
 /* Generic stack tracer with callbacks */
 
 struct stacktrace_ops {
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index d3802ee..c223b7e 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2336,7 +2336,7 @@ static const struct stacktrace_ops backtrace_ops = {
 	.warning_symbol		= backtrace_warning_symbol,
 	.stack			= backtrace_stack,
 	.address		= backtrace_address,
-	.walk_stack		= print_context_stack,
+	.walk_stack		= print_context_stack_bp,
 };
 
 #include "../dumpstack.h"
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 8aaa119..c56bc28 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -109,6 +109,30 @@ print_context_stack(struct thread_info *tinfo,
 	}
 	return bp;
 }
+EXPORT_SYMBOL_GPL(print_context_stack);
+
+unsigned long
+print_context_stack_bp(struct thread_info *tinfo,
+		       unsigned long *stack, unsigned long bp,
+		       const struct stacktrace_ops *ops, void *data,
+		       unsigned long *end, int *graph)
+{
+	struct stack_frame *frame = (struct stack_frame *)bp;
+	unsigned long *ret_addr = &frame->return_address;
+
+	while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) {
+		unsigned long addr = *ret_addr;
+
+		if (__kernel_text_address(addr)) {
+			ops->address(data, addr, 1);
+			frame = frame->next_frame;
+			ret_addr = &frame->return_address;
+			print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
+		}
+	}
+	return (unsigned long)frame;
+}
+EXPORT_SYMBOL_GPL(print_context_stack_bp);
 
 
 static void
@@ -143,8 +167,8 @@ static void print_trace_address(void *data, unsigned long addr, int reliable)
 static const struct stacktrace_ops print_trace_ops = {
 	.warning		= print_trace_warning,
 	.warning_symbol		= print_trace_warning_symbol,
-	.stack 			= print_trace_stack,
-	.address 		= print_trace_address,
+	.stack			= print_trace_stack,
+	.address		= print_trace_address,
 	.walk_stack		= print_context_stack,
 };